Paper Citation Record · LEDGER

Should LLM Safety Be More Than Refusing Harmful Instructions?

As of 22 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2506.02442.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.02442 v2

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:27:47.482807Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

48 of 48 outbound references displayed

verified exact3
verified fuzzy2
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4f626177-35eb-4ab9-bd5b-a0c7274a307b · outbound

This paper cites GPT-4 Technical Report.

Should LLM Safety Be More Than Refusing Harmful Instructions? GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.122877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52404c4d-5d6a-471e-a625-cda4dadbb19f · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:50.178348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ae55402e-b8c8-4b91-8a4b-b978302c4afb · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Should LLM Safety Be More Than Refusing Harmful Instructions? Detecting Language Model Attacks with Perplexity

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.137122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04624ff3-35b9-404b-ab65-c8b96582c804 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? Gemini: A Family of Highly Capable Multimodal Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.144854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc9f277e-c466-46c5-ac76-a412e39331ef · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:50.095009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a2c1901f-66e2-4c83-a48e-6db1d4fb6c5c · outbound

This paper cites Jailbreaking Large Language Models with Symbolic Mathematics.

Should LLM Safety Be More Than Refusing Harmful Instructions? Jailbreaking Large Language Models with Symbolic Mathematics

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.159009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11eae64-55f7-45ac-b29d-bf93198671f2 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.166556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb14b9f-4929-4411-a53d-120cf8f8b928 · outbound

This paper cites Pappas, Florian Tram\` e r, Hamed Hassani, and Eric Wong.

Should LLM Safety Be More Than Refusing Harmful Instructions? Pappas, Florian Tram\` e r, Hamed Hassani, and Eric Wong

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:27:49.928300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c43bbd36-f338-4770-bffb-980105f6b432 · outbound

This paper cites Pappas, Florian Tram \`e r, Hamed Hassani, and Eric Wong.

Should LLM Safety Be More Than Refusing Harmful Instructions? Pappas, Florian Tram \`e r, Hamed Hassani, and Eric Wong

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:27:49.777409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3ecfed4b-90af-4563-bbef-b163fb4546b3 · outbound

This paper cites Recent Advances in Attack and Defense Approaches of Large Language Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? Recent Advances in Attack and Defense Approaches of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.188977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca62124-816a-4f1f-9737-e4b7ec72e693 · outbound

This paper cites Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.

Should LLM Safety Be More Than Refusing Harmful Instructions? Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.195714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b7078e-91a8-422d-af32-06c9c369cce8 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 12

Resolution: verified exact; doi, observed 2026-08-07T11:27:47.649065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 72ae24e7-ab71-481b-9ca2-3158ebd550e2 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:49.647650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 88b1e8b6-d140-46b4-a892-d0a8b718f7a3 · outbound

This paper cites Unsupervised Cipher Cracking Using Discrete GANs.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unsupervised Cipher Cracking Using Discrete GANs

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:27:48.698390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30ab4d27-9b68-4ebd-98b4-569097c9ddc8 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Should LLM Safety Be More Than Refusing Harmful Instructions? DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.235852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567d72f0-94fd-42bf-9c2d-ba662c14ee19 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:49.501436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b07cb090-4083-40a9-ae2b-5094165514ae · outbound

This paper cites competency.

Should LLM Safety Be More Than Refusing Harmful Instructions? competency

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.250751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f21550f7-2f32-4419-af9e-5c182045b666 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.259907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5444761c-5f45-403b-93b7-032d835e6c19 · outbound

This paper cites Endless Jailbreaks with Bijection Learning.

Should LLM Safety Be More Than Refusing Harmful Instructions? Endless Jailbreaks with Bijection Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.272740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b28cec-7931-4bd0-ab13-fd3bf806ad74 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Should LLM Safety Be More Than Refusing Harmful Instructions? Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.280600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d449b9ff-6312-494c-9fce-64e26117404f · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.286452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73344d01-9c0e-4c79-b7c9-733d12031035 · outbound

This paper cites Mistral 7B.

Should LLM Safety Be More Than Refusing Harmful Instructions? Mistral 7B

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.295083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7093f919-ff68-48f4-8443-7131b57c8455 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

Should LLM Safety Be More Than Refusing Harmful Instructions? ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.302318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5aaf8e2-e118-45dc-a18d-0d865ef72af0 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.310189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25be7c48-77af-4c52-8fb1-e932c0bf2cd7 · outbound

This paper cites CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges.

Should LLM Safety Be More Than Refusing Harmful Instructions? CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.317124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3919f68-8a83-4a68-bfdd-33df43cb7dea · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.325604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b091d066-6201-4946-a08c-2e603dcaceda · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.338065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642d42cb-e567-4d53-81b7-f1669b2ff556 · outbound

This paper cites Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities.

Should LLM Safety Be More Than Refusing Harmful Instructions? Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.346115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855c9b16-6bc5-494d-a596-913432d3e6df · outbound

This paper cites SaRO: Enhancing LLM Safety through Reasoning-based Alignment.

Should LLM Safety Be More Than Refusing Harmful Instructions? SaRO: Enhancing LLM Safety through Reasoning-based Alignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.354047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83d5f35-8bbc-474d-88e1-43945ded8fd0 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 30

Resolution: verified exact; raw_fallback, observed 2026-08-07T11:27:48.173546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e64ce843-07d1-48f9-a367-3428c3f2529b · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.375342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd256c9-e1ec-46b8-ada0-20f9e9743acd · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.381480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9f0039-c899-41fd-96e7-deba8fd39018 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:49.399243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 97a19b08-9b36-452a-b4f3-21651ea0bb56 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.393410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b9643af-eeed-44d3-97cf-291528fbb9bd · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:49.272487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 28416321-807b-4036-978f-a1716094620e · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Should LLM Safety Be More Than Refusing Harmful Instructions? LLaMA: Open and Efficient Foundation Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.405477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3299d20c-9e50-4068-9f5b-e6512fbb7019 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.412052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83349e79-5cd6-4017-b2b7-2d15e981583f · outbound

This paper cites Dai, and Quoc V Le.

Should LLM Safety Be More Than Refusing Harmful Instructions? Dai, and Quoc V Le

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.418202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 210a72bd-66f7-41e1-b106-a2140787b95f · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.424467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfd2488b-dc86-4db2-b031-d07166648d10 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:27:49.018405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3f819ca3-cc5c-413f-bf67-8f459f50fc71 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.435792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 309629fa-7449-4a7c-9598-8fb71354e27a · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.443024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b54cedb5-02a6-4160-b10b-f12f9acbbc3f · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.449114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c32352f6-5eb5-42a8-8ed4-8f8deedc95e8 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.454913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e57b8c6-f9cd-4a4b-b2f0-07c74fd00440 · outbound

This paper cites an unresolved cited work.

Should LLM Safety Be More Than Refusing Harmful Instructions? Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.461431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86e2506d-b829-49ed-8cf4-cd50cc697115 · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Should LLM Safety Be More Than Refusing Harmful Instructions? BERTScore: Evaluating Text Generation with BERT

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.467267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 411437fe-d19a-48b6-a933-82d84bff3c92 · outbound

This paper cites online" 'onlinestring :=.

Should LLM Safety Be More Than Refusing Harmful Instructions? online" 'onlinestring :=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.475035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d16e431-eaa6-413b-a14e-88b605b2ba9d · outbound

This paper cites write newline.

Should LLM Safety Be More Than Refusing Harmful Instructions? write newline

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:27:47.482807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.